diff options
Diffstat (limited to 'llvm/test/CodeGen/X86/madd.ll')
| -rw-r--r-- | llvm/test/CodeGen/X86/madd.ll | 48 |
1 files changed, 17 insertions, 31 deletions
diff --git a/llvm/test/CodeGen/X86/madd.ll b/llvm/test/CodeGen/X86/madd.ll index 8c1f90461dd..773a42f6c0e 100644 --- a/llvm/test/CodeGen/X86/madd.ll +++ b/llvm/test/CodeGen/X86/madd.ll @@ -1876,26 +1876,12 @@ define <4 x i32> @larger_mul(<16 x i16> %A, <16 x i16> %B) { ; ; AVX1-LABEL: larger_mul: ; AVX1: # %bb.0: -; AVX1-NEXT: vpmovsxwd %xmm0, %xmm2 -; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1] -; AVX1-NEXT: vpmovsxwd %xmm0, %xmm0 -; AVX1-NEXT: vpackssdw %xmm0, %xmm2, %xmm0 -; AVX1-NEXT: vpmovsxwd %xmm1, %xmm2 -; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1] -; AVX1-NEXT: vpmovsxwd %xmm1, %xmm1 -; AVX1-NEXT: vpackssdw %xmm1, %xmm2, %xmm1 ; AVX1-NEXT: vpmaddwd %xmm1, %xmm0, %xmm0 ; AVX1-NEXT: vzeroupper ; AVX1-NEXT: retq ; ; AVX2-LABEL: larger_mul: ; AVX2: # %bb.0: -; AVX2-NEXT: vpmovsxwd %xmm0, %ymm0 -; AVX2-NEXT: vpmovsxwd %xmm1, %ymm1 -; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2 -; AVX2-NEXT: vpackssdw %xmm2, %xmm1, %xmm1 -; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2 -; AVX2-NEXT: vpackssdw %xmm2, %xmm0, %xmm0 ; AVX2-NEXT: vpmaddwd %xmm1, %xmm0, %xmm0 ; AVX2-NEXT: vzeroupper ; AVX2-NEXT: retq @@ -2597,29 +2583,29 @@ define <4 x i32> @pmaddwd_bad_indices(<8 x i16>* %Aptr, <8 x i16>* %Bptr) { ; SSE2: # %bb.0: ; SSE2-NEXT: movdqa (%rdi), %xmm0 ; SSE2-NEXT: movdqa (%rsi), %xmm1 -; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm1[0,2,2,3,4,5,6,7] -; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7] +; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm0[2,1,2,3,4,5,6,7] +; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,6,5,6,7] ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3] -; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm0[2,1,2,3,4,5,6,7] -; SSE2-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,6,5,6,7] -; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3] -; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[1,0,3,2,4,5,6,7] -; SSE2-NEXT: movdqa %xmm3, %xmm4 -; SSE2-NEXT: pmulhw %xmm2, %xmm4 -; SSE2-NEXT: pmullw %xmm2, %xmm3 -; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3] +; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[1,0,3,2,4,5,6,7] ; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,3,2,3,4,5,6,7] ; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,7,6,7] ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] +; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm1[0,2,2,3,4,5,6,7] +; SSE2-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,4,6,6,7] +; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3] ; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7] ; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,7,5,6,7] ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3] ; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[1,0,3,2,4,5,6,7] -; SSE2-NEXT: movdqa %xmm0, %xmm2 -; SSE2-NEXT: pmulhw %xmm1, %xmm2 +; SSE2-NEXT: movdqa %xmm2, %xmm4 +; SSE2-NEXT: pmulhw %xmm3, %xmm4 +; SSE2-NEXT: pmullw %xmm3, %xmm2 +; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3] +; SSE2-NEXT: movdqa %xmm0, %xmm3 +; SSE2-NEXT: pmulhw %xmm1, %xmm3 ; SSE2-NEXT: pmullw %xmm1, %xmm0 -; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] -; SSE2-NEXT: paddd %xmm3, %xmm0 +; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3] +; SSE2-NEXT: paddd %xmm2, %xmm0 ; SSE2-NEXT: retq ; ; AVX-LABEL: pmaddwd_bad_indices: @@ -2627,13 +2613,13 @@ define <4 x i32> @pmaddwd_bad_indices(<8 x i16>* %Aptr, <8 x i16>* %Bptr) { ; AVX-NEXT: vmovdqa (%rdi), %xmm0 ; AVX-NEXT: vmovdqa (%rsi), %xmm1 ; AVX-NEXT: vpshufb {{.*#+}} xmm2 = xmm0[2,3,4,5,10,11,12,13,12,13,10,11,12,13,14,15] -; AVX-NEXT: vpmovsxwd %xmm2, %xmm2 +; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,6,7,8,9,14,15,8,9,14,15,12,13,14,15] ; AVX-NEXT: vpshufb {{.*#+}} xmm3 = xmm1[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15] +; AVX-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15] +; AVX-NEXT: vpmovsxwd %xmm2, %xmm2 ; AVX-NEXT: vpmovsxwd %xmm3, %xmm3 ; AVX-NEXT: vpmulld %xmm3, %xmm2, %xmm2 -; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,6,7,8,9,14,15,8,9,14,15,12,13,14,15] ; AVX-NEXT: vpmovsxwd %xmm0, %xmm0 -; AVX-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15] ; AVX-NEXT: vpmovsxwd %xmm1, %xmm1 ; AVX-NEXT: vpmulld %xmm1, %xmm0, %xmm0 ; AVX-NEXT: vpaddd %xmm0, %xmm2, %xmm0 |
